Short-term load forecasting based on Elman Neural Network optimized by Firefly Algorithm

The load of power system usually presents a certain range of nonlinear fluctuation with time, but the load characteristics in power system still have certain rules. Therefore, this paper presents a Firefly Algorithm to optimize the short-term load forecasting model of Elman Neural Network, in order to improve the accuracy of load forecasting. Firstly, the nonlinear optimization ability of Firefly Algorithm is utilized to optimize the weights and thresholds of Elman Neural Network, to overcome the shortage of the Elman Neural Network easily plunging into local optimum. Then, make use of the optimized weights and thresholds to enhance the fitting ability of Elman Neural Network. Finally, the simulation results show that the Elman Neural Network optimized by Firefly Algorithm has higher prediction accuracy than the traditional Elman Neural Network.